© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15128
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     A
    -24.13
    _a
    -22.50
    aq
    -22.38
    -A
    -22.25
    *A
    -22.13
    +A
    -21.63
    aque
    -21.63
    >A
    -21.38
    _A
    -20.88
    à
    -20.38
    POSITIVE LOGITS
    迟
    14.81
    есь
    13.69
    eness
    12.88
    eds
    12.88
    -loading
    12.81
    -commit
    12.69
    Eb
    12.63
    本能
    12.63
    勃
    12.63
     committing
    12.56
    Activations Density 0.377%

    No Known Activations